#GPU_acceleration

[phonemantra-blog]

It will be built next year The European Union will soon have its first exascale supercomputer. It is reported that the configuration of the system, called Jupiter, has been completed, and the authors of the project have chosen Nvidia accelerators and SiPearl Rhea processors (Neoverse V1 platform) on the Arm architecture. [caption id="attachment_64466" align="aligncenter" width="780"] Nvidia accelerators and Arm processors[/caption] The Jupiter system will be based on Nvidia accelerators and Arm processors The development is being managed by the European High-Performance Computing Joint Undertaking (EuroHPC JU) and a group of technology firms consisting of Eviden and ParTec. The system will be built at the Jülich Supercomputing Center, located near Munich. Construction will begin in early 2024. By the way, it should be noted that Jupiter will be the first exascale supercomputer built on Arm processors. One of the features of Jupiter will be its modularity, which will allow owners to further increase the power of the system, including through completely different components, that is, AMD accelerators and x86-compatible processors. The installation cost will be 273 million euros.

[phonemantra-blog]

And almost 15 times faster than AI At the System LSI Tech Day 2023 event, Samsung talked about the upcoming Exynos 2400 single-chip system. [caption id="attachment_64092" align="aligncenter" width="600"] GPU[/caption] For example, it is now known for sure that the graphics core of the new SoC is called Xclipse 940, and it is based on the AMD RDNA 3 architecture. Let us recall that new data suggests that Samsung will continue to develop its GPUs based on AMD technologies. CPU 1.7 times faster than Exynos 2200, and GPU based on RDNA 3 architecture The performance of the Exynos 2400 processor has increased by an impressive 70% compared to the Exynos 2200, but it is worth remembering that the Exynos 2200 was released not last year, but almost two years ago. AI performance increased 14.7 times. For now, that's all we've been told, but from other leaks we know that the new SoC will have a 10-core CPU, and the performance will be significantly lower than that of the upcoming Snapdragon 8 Gen 3.

[phonemantra-blog]

But there is no shortage of gaming video cards The shortage of gaming video cards has given way to a shortage of GPUs for working with artificial intelligence. And this deficit will also drag on. [caption id="attachment_53701" align="alignnone" width="780"] Nvidia[/caption] According to TSMC, which produces its current generation of graphics processors for Nvidia, the shortage of Nvidia accelerators for AI will continue for about another year and a half. The problem is due to limitations in the capacity of chip packaging using CoWoS packaging technology, which cannot be quickly solved. The shortage of Nvidia accelerators for AI will continue for another year and a half It's not a lack of AI chips, but a lack of CoWoS capabilities. Currently, we cannot satisfy 100% of our customers' needs, but we try to maintain around 80%. We think this is a temporary phenomenon that will last about a year and a half TSMC notes that demand for CoWoS packaging unexpectedly increased at the beginning of this year. It was then that the boom in generative AI began and, as a result, the increase in demand for Nvidia accelerators. TSMC is currently installing additional tools for CoWoS in its existing factories, but this takes time.

[phonemantra-blog]

True, subject to effective use US sanctions that prohibit the supply of Nvidia's latest (and not-so-newest) accelerators to China don't seem to bother everyone. Tencent reported that it has managed to accumulate so many adapters that it will now last for a long time.  The company's president said that the reserves are such that Tencent will have enough to continue developing its Hunyuan artificial intelligence model. Moreover, it will be enough, as the head of the Chinese giant put it, for at least another couple of generations. That is, for several years.  Chinese Tencent has accumulated so many Nvidia accelerators that it will last for a couple of generations to come [caption id="attachment_82888" align="aligncenter" width="600"] Nvidia accelerators[/caption] True, even if the company now thinks so, how correct their assessments are, given the pace of industry development, is an open question.  But the company notes that it needs to find ways to use existing accelerators more efficiently. In addition, Tencent will be looking for or waiting for the emergence of worthy domestic accelerators.